rewirebio.iobenchmarks

Biological models

Understand model architectures, biological inputs, access requirements and the evidence from linked evaluations.

374 model records in release 2026-11-21-c8bea25e5abb (release manifest, gzip). Showing 361–374; page 16 of 16.

Evaluated configurations, methods and pipelines are listed separately. Names alone do not establish equivalent models or checkpoints.

  • Uni-RNA

    RNA and transcriptomes

    Uni-RNA RNA foundation model (L8, L12 and L16 checkpoints).

  • Unirep

    Proteins and complexes

    Deep learning representation of protein sequences learned from unlabeled amino-acid sequences, on which simple models predict stability and mutant function, scored in ProteinGym as a zero-shot single-sequence substitution baseline.

  • Unirep evotuned

    Proteins and complexes

    Evo-tuned variant of UniRep, a protein sequence representation learned from unlabeled amino-acid sequences, which ProteinGym lists as using a multiple sequence alignment for evo-tuning and scores as a zero-shot substitution baseline.

  • UniSpec

    Proteins and complexes

    UniSpec attention-based fragment dictionary model (about 12M parameters).

  • UTR-LM

    DNA and genomes

    Language model pre-trained on 5' untranslated region sequence.

  • VenusREM

    Proteins and complexes

    Retrieval-enhanced protein language model that captures local amino acid interactions for mutation effect prediction, scored in ProteinGym as a zero-shot substitution baseline from alignment and structure inputs.

  • VESPA

    Proteins and complexes

    Logistic regression ensemble that predicts single amino acid variant effects without alignments from protein language model embeddings, combining predicted conservation, BLOSUM62 scores and language-model mask reconstruction probabilities; scored in ProteinGym as a zero-shot substitution baseline.

  • VespaG

    Proteins and complexes

    Missense variant effect predictor that feeds protein language model embeddings to a minimal deep learning model trained on GEMME predictions for 39 million human variants, scored in ProteinGym as a substitution baseline.

  • VESPAl

    Proteins and complexes

    Light version of VESPA that predicts single amino acid variant effects from predicted conservation and BLOSUM62 scores only, without the language-model substitution probabilities, scored in ProteinGym as a zero-shot substitution baseline.

  • ViroCaduceus

    Microbes and communities · DNA and genomes

    Caduceus-architecture model pretrained on viral sequences by the ViroBench authors (in-house model).

  • ViroDNABERT2

    Microbes and communities · DNA and genomes

    DNABERT-2-architecture model pretrained on viral sequences by the ViroBench authors (in-house model).

  • ViroHyena

    Microbes and communities · DNA and genomes

    Hyena-architecture nucleotide model pretrained on viral sequences by the ViroBench authors (in-house model).

  • Wavenet

    Proteins and complexes

    Alignment-free autoregressive deep generative model of protein sequences adapted from natural language processing that predicts missense and indel effects, scored in ProteinGym as a zero-shot substitution baseline.

  • xTrimoPGLM

    Proteins and complexes

    Family of protein language models, scaled up to 100 billion parameters, pretrained jointly with autoencoding and autoregressive objectives for protein understanding and generation; ProteinGym scores several sizes as zero-shot single-sequence substitution baselines.

This index reflects a dated catalogue, not an exhaustive census. Source checking does not mean independent reproduction; compare results only under compatible protocols, datasets and metrics.